[llvm] 4762f3b - [RISCV][TTI] Add cost of type based binOp VP intrinsics with functionalOPC. (#93435)

via llvm-commits llvm-commits at lists.llvm.org
Thu Jul 4 17:13:22 PDT 2024


Author: Elvis Wang
Date: 2024-07-05T08:13:18+08:00
New Revision: 4762f3bab05768123e7fbf6a5408a2418c52e31c

URL: https://github.com/llvm/llvm-project/commit/4762f3bab05768123e7fbf6a5408a2418c52e31c
DIFF: https://github.com/llvm/llvm-project/commit/4762f3bab05768123e7fbf6a5408a2418c52e31c.diff

LOG: [RISCV][TTI] Add cost of type based binOp VP intrinsics with functionalOPC. (#93435)

Intrinsics not supported in the backend will fall Into BasicTTIImpl,
which will check if the VP intrinsic is a type based instruction.
All type based instruction will fall into the
`getTypeBasedIntrinsicInstrCost()` which doesn't support instruction
with scalable vector type.

This patch adds the instruction cost for type based binOp VP intrinsic
instructions in the backend to get the valid instruction costs.
The cost of type based binOp VP intrinsics will be same as their non-VP
counterpart.

Added: 
    

Modified: 
    llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
    llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
    llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll

Removed: 
    


################################################################################
diff  --git a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
index 176d0e79253acb..d603138773de4b 100644
--- a/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
+++ b/llvm/lib/Target/RISCV/RISCVTargetTransformInfo.cpp
@@ -959,6 +959,32 @@ RISCVTTIImpl::getIntrinsicInstrCost(const IntrinsicCostAttributes &ICA,
       return Cost * LT.first;
     break;
   }
+  // vp integer arithmetic ops.
+  case Intrinsic::vp_add:
+  case Intrinsic::vp_and:
+  case Intrinsic::vp_ashr:
+  case Intrinsic::vp_lshr:
+  case Intrinsic::vp_mul:
+  case Intrinsic::vp_or:
+  case Intrinsic::vp_sdiv:
+  case Intrinsic::vp_shl:
+  case Intrinsic::vp_srem:
+  case Intrinsic::vp_sub:
+  case Intrinsic::vp_udiv:
+  case Intrinsic::vp_urem:
+  case Intrinsic::vp_xor:
+  // vp float arithmetic ops.
+  case Intrinsic::vp_fadd:
+  case Intrinsic::vp_fsub:
+  case Intrinsic::vp_fmul:
+  case Intrinsic::vp_fdiv:
+  case Intrinsic::vp_frem: {
+    std::optional<unsigned> FOp =
+        VPIntrinsic::getFunctionalOpcodeForVP(ICA.getID());
+    if (FOp)
+      return getArithmeticInstrCost(*FOp, ICA.getReturnType(), CostKind);
+    break;
+  }
   }
 
   if (ST->hasVInstructions() && RetTy->isVectorTy()) {

diff  --git a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
index a23ea00dbaa75d..87ffb23dcb88e2 100644
--- a/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
+++ b/llvm/test/Analysis/CostModel/RISCV/rvv-intrinsics.ll
@@ -1,11 +1,17 @@
 ; NOTE: Assertions have been autogenerated by utils/update_analyze_test_checks.py
 ; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v | FileCheck %s
+; RUN: opt < %s -passes="print<cost-model>" 2>&1 -disable-output -S -mtriple=riscv64 -mattr=+v --type-based-intrinsic-cost=true | FileCheck %s --check-prefixes=TYPEBASED
 
 define void @unsupported_fp_ops(<vscale x 4 x float> %vec, i32 %extraarg) {
 ; CHECK-LABEL: 'unsupported_fp_ops'
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'unsupported_fp_ops'
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 %extraarg)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
 
   %pow = call <vscale x 4 x float> @llvm.pow.nxv4f32(<vscale x 4 x float> %vec, <vscale x 4 x float> %vec)
@@ -17,6 +23,10 @@ define void @powi(<vscale x 4 x float> %vec) {
 ; CHECK-LABEL: 'powi'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'powi'
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %powi = call <vscale x 4 x float> @llvm.powi.nxv4f32.i32(<vscale x 4 x float> %vec, i32 42)
   ret void
@@ -26,6 +36,10 @@ define void @fshr(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i3
 ; CHECK-LABEL: 'fshr'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %1 = call <vscale x 1 x i32> @llvm.fshr.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'fshr'
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %1 = call <vscale x 1 x i32> @llvm.fshr.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <vscale x 1 x i32> @llvm.fshr.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
   ret void
@@ -35,6 +49,10 @@ define void @fshl(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i3
 ; CHECK-LABEL: 'fshl'
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %1 = call <vscale x 1 x i32> @llvm.fshl.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'fshl'
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %1 = call <vscale x 1 x i32> @llvm.fshl.nxv1i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <vscale x 1 x i32> @llvm.fshl.nxv4i32(<vscale x 1 x i32> %a, <vscale x 1 x i32> %b, <vscale x 1 x i32> %c)
   ret void
@@ -81,6 +99,47 @@ define void @vp_fshr() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'vp_fshr'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x i8> @llvm.vp.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x i8> @llvm.vp.fshr.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x i8> @llvm.vp.fshr.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x i8> @llvm.vp.fshr.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.fshr.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.fshr.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.fshr.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.fshr.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshr.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshr.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshr.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.vp.fshr.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.vp.fshr.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.vp.fshr.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x i16> @llvm.vp.fshr.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.fshr.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.fshr.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.fshr.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshr.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshr.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshr.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.vp.fshr.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.vp.fshr.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %24 = call <8 x i32> @llvm.vp.fshr.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %25 = call <16 x i32> @llvm.vp.fshr.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.vp.fshr.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.vp.fshr.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshr.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshr.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshr.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.vp.fshr.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %32 = call <4 x i64> @llvm.vp.fshr.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %33 = call <8 x i64> @llvm.vp.fshr.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %34 = call <16 x i64> @llvm.vp.fshr.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.vp.fshr.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshr.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshr.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshr.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <2 x i8> @llvm.vp.fshr.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
   call <4 x i8> @llvm.vp.fshr.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
@@ -164,6 +223,47 @@ define void @vp_fshl() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'vp_fshl'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %1 = call <2 x i8> @llvm.vp.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %2 = call <4 x i8> @llvm.vp.fshl.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %3 = call <8 x i8> @llvm.vp.fshl.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %4 = call <16 x i8> @llvm.vp.fshl.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %5 = call <vscale x 1 x i8> @llvm.vp.fshl.nxv1i8(<vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i8> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %6 = call <vscale x 2 x i8> @llvm.vp.fshl.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %7 = call <vscale x 4 x i8> @llvm.vp.fshl.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %8 = call <vscale x 8 x i8> @llvm.vp.fshl.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %9 = call <vscale x 16 x i8> @llvm.vp.fshl.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %10 = call <vscale x 32 x i8> @llvm.vp.fshl.nxv32i8(<vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i8> undef, <vscale x 32 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %11 = call <vscale x 64 x i8> @llvm.vp.fshl.nxv64i8(<vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i8> undef, <vscale x 64 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %12 = call <2 x i16> @llvm.vp.fshl.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %13 = call <4 x i16> @llvm.vp.fshl.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %14 = call <8 x i16> @llvm.vp.fshl.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %15 = call <16 x i16> @llvm.vp.fshl.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %16 = call <vscale x 1 x i16> @llvm.vp.fshl.nxv1i16(<vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i16> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %17 = call <vscale x 2 x i16> @llvm.vp.fshl.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %18 = call <vscale x 4 x i16> @llvm.vp.fshl.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %19 = call <vscale x 8 x i16> @llvm.vp.fshl.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %20 = call <vscale x 16 x i16> @llvm.vp.fshl.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %21 = call <vscale x 32 x i16> @llvm.vp.fshl.nxv32i16(<vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i16> undef, <vscale x 32 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %22 = call <2 x i32> @llvm.vp.fshl.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %23 = call <4 x i32> @llvm.vp.fshl.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %24 = call <8 x i32> @llvm.vp.fshl.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %25 = call <16 x i32> @llvm.vp.fshl.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %26 = call <vscale x 1 x i32> @llvm.vp.fshl.nxv1i32(<vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i32> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %27 = call <vscale x 2 x i32> @llvm.vp.fshl.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %28 = call <vscale x 4 x i32> @llvm.vp.fshl.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %29 = call <vscale x 8 x i32> @llvm.vp.fshl.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %30 = call <vscale x 16 x i32> @llvm.vp.fshl.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %31 = call <2 x i64> @llvm.vp.fshl.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %32 = call <4 x i64> @llvm.vp.fshl.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %33 = call <8 x i64> @llvm.vp.fshl.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %34 = call <16 x i64> @llvm.vp.fshl.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %35 = call <vscale x 1 x i64> @llvm.vp.fshl.nxv1i64(<vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i64> undef, <vscale x 1 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %36 = call <vscale x 2 x i64> @llvm.vp.fshl.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %37 = call <vscale x 4 x i64> @llvm.vp.fshl.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %38 = call <vscale x 8 x i64> @llvm.vp.fshl.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <2 x i8> @llvm.vp.fshl.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
   call <4 x i8> @llvm.vp.fshl.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
@@ -216,31 +316,130 @@ define void @add() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = add <8 x i8> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = add <16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = add <2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t10 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t12 = add <4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t13 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t14 = add <8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t15 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t16 = add <16 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = add <vscale x 2 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t20 = add <vscale x 4 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t22 = add <vscale x 8 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t24 = add <vscale x 16 x i8> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = add <vscale x 2 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = add <vscale x 4 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = add <vscale x 8 x i64> undef, undef
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = add <vscale x 16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = add <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t11 = add <4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t13 = add <8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t15 = add <16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = add <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = add <4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t21 = add <8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t23 = add <16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t25 = add <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t27 = add <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t29 = add <8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t31 = add <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t33 = add <vscale x 2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t35 = add <vscale x 4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t37 = add <vscale x 8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t39 = add <vscale x 16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.add.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t41 = add <vscale x 2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.add.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t43 = add <vscale x 4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.add.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t45 = add <vscale x 8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.add.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t47 = add <vscale x 16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.add.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t49 = add <vscale x 2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t51 = add <vscale x 4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.add.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t53 = add <vscale x 8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.add.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t55 = add <vscale x 16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t57 = add <vscale x 2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t59 = add <vscale x 4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t61 = add <vscale x 8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t63 = add <vscale x 16 x i64> undef, undef
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'add'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = add <2 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.add.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = add <4 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.add.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = add <8 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = add <16 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = add <2 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t11 = add <4 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t13 = add <8 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t15 = add <16 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = add <2 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = add <4 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t21 = add <8 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t23 = add <16 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t25 = add <2 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t27 = add <4 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t29 = add <8 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t31 = add <16 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t33 = add <vscale x 2 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t35 = add <vscale x 4 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t37 = add <vscale x 8 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t39 = add <vscale x 16 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.add.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t41 = add <vscale x 2 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.add.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t43 = add <vscale x 4 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.add.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t45 = add <vscale x 8 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.add.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t47 = add <vscale x 16 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.add.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t49 = add <vscale x 2 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t51 = add <vscale x 4 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.add.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t53 = add <vscale x 8 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.add.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t55 = add <vscale x 16 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t57 = add <vscale x 2 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t59 = add <vscale x 4 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t61 = add <vscale x 8 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t63 = add <vscale x 16 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.vp.add.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
   %t1 = add <2 x i8> undef, undef
@@ -250,30 +449,263 @@ define void @add() {
   %t5 = add <8 x i8> undef, undef
   %t6 = call <16 x i8> @llvm.vp.add.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
   %t7 = add <16 x i8> undef, undef
-  %t8 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
-  %t9 = add <2 x i64> undef, undef
-  %t10 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
-  %t12 = add <4 x i64> undef, undef
-  %t13 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
-  %t14 = add <8 x i64> undef, undef
-  %t15 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
-  %t16 = add <16 x i64> undef, undef
-  %t17 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
-  %t18 = add <vscale x 2 x i8> undef, undef
-  %t19 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
-  %t20 = add <vscale x 4 x i8> undef, undef
-  %t21 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
-  %t22 = add <vscale x 8 x i8> undef, undef
-  %t23 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
-  %t24 = add <vscale x 16 x i8> undef, undef
-  %t25 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
-  %t26 = add <vscale x 2 x i64> undef, undef
-  %t27 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
-  %t28 = add <vscale x 4 x i64> undef, undef
-  %t29 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
-  %t30 = add <vscale x 8 x i64> undef, undef
-  %t31 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
-  %t32 = add <vscale x 16 x i64> undef, undef
+  %t8 = call <2 x i16> @llvm.vp.add.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+  %t9 = add <2 x i16> undef, undef
+  %t10 = call <4 x i16> @llvm.vp.add.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+  %t11 = add <4 x i16> undef, undef
+  %t12 = call <8 x i16> @llvm.vp.add.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+  %t13 = add <8 x i16> undef, undef
+  %t14 = call <16 x i16> @llvm.vp.add.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+  %t15 = add <16 x i16> undef, undef
+  %t16 = call <2 x i32> @llvm.vp.add.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+  %t17 = add <2 x i32> undef, undef
+  %t18 = call <4 x i32> @llvm.vp.add.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+  %t19 = add <4 x i32> undef, undef
+  %t20 = call <8 x i32> @llvm.vp.add.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+  %t21 = add <8 x i32> undef, undef
+  %t22 = call <16 x i32> @llvm.vp.add.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+  %t23 = add <16 x i32> undef, undef
+  %t24 = call <2 x i64> @llvm.vp.add.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+  %t25 = add <2 x i64> undef, undef
+  %t26 = call <4 x i64> @llvm.vp.add.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+  %t27 = add <4 x i64> undef, undef
+  %t28 = call <8 x i64> @llvm.vp.add.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+  %t29 = add <8 x i64> undef, undef
+  %t30 = call <16 x i64> @llvm.vp.add.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+  %t31 = add <16 x i64> undef, undef
+  %t32 = call <vscale x 2 x i8> @llvm.vp.add.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t33 = add <vscale x 2 x i8> undef, undef
+  %t34 = call <vscale x 4 x i8> @llvm.vp.add.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t35 = add <vscale x 4 x i8> undef, undef
+  %t36 = call <vscale x 8 x i8> @llvm.vp.add.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t37 = add <vscale x 8 x i8> undef, undef
+  %t38 = call <vscale x 16 x i8> @llvm.vp.add.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t39 = add <vscale x 16 x i8> undef, undef
+  %t40 = call <vscale x 2 x i16> @llvm.vp.add.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t41 = add <vscale x 2 x i16> undef, undef
+  %t42 = call <vscale x 4 x i16> @llvm.vp.add.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t43 = add <vscale x 4 x i16> undef, undef
+  %t44 = call <vscale x 8 x i16> @llvm.vp.add.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t45 = add <vscale x 8 x i16> undef, undef
+  %t46 = call <vscale x 16 x i16> @llvm.vp.add.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t47 = add <vscale x 16 x i16> undef, undef
+  %t48 = call <vscale x 2 x i32> @llvm.vp.add.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t49 = add <vscale x 2 x i32> undef, undef
+  %t50 = call <vscale x 4 x i32> @llvm.vp.add.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t51 = add <vscale x 4 x i32> undef, undef
+  %t52 = call <vscale x 8 x i32> @llvm.vp.add.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t53 = add <vscale x 8 x i32> undef, undef
+  %t54 = call <vscale x 16 x i32> @llvm.vp.add.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t55 = add <vscale x 16 x i32> undef, undef
+  %t56 = call <vscale x 2 x i64> @llvm.vp.add.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t57 = add <vscale x 2 x i64> undef, undef
+  %t58 = call <vscale x 4 x i64> @llvm.vp.add.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t59 = add <vscale x 4 x i64> undef, undef
+  %t60 = call <vscale x 8 x i64> @llvm.vp.add.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t61 = add <vscale x 8 x i64> undef, undef
+  %t62 = call <vscale x 16 x i64> @llvm.vp.add.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t63 = add <vscale x 16 x i64> undef, undef
+  ret void
+}
+
+define void @and() {
+; CHECK-LABEL: 'and'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.and.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = and <2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.and.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = and <4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.and.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = and <8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.and.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = and <16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.and.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = and <2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.and.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t11 = and <4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.and.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t13 = and <8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.and.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t15 = and <16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.and.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = and <2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = and <4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t21 = and <8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.and.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t23 = and <16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.and.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t25 = and <2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.and.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t27 = and <4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.and.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t29 = and <8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.and.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t31 = and <16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.and.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t33 = and <vscale x 2 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.and.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t35 = and <vscale x 4 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.and.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t37 = and <vscale x 8 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.and.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t39 = and <vscale x 16 x i8> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.and.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t41 = and <vscale x 2 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.and.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t43 = and <vscale x 4 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.and.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t45 = and <vscale x 8 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.and.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t47 = and <vscale x 16 x i16> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.and.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t49 = and <vscale x 2 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t51 = and <vscale x 4 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.and.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t53 = and <vscale x 8 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.and.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t55 = and <vscale x 16 x i32> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.and.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t57 = and <vscale x 2 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.and.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t59 = and <vscale x 4 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.and.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t61 = and <vscale x 8 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.and.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t63 = and <vscale x 16 x i64> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'and'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x i8> @llvm.vp.and.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = and <2 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x i8> @llvm.vp.and.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = and <4 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t4 = call <8 x i8> @llvm.vp.and.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = and <8 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t6 = call <16 x i8> @llvm.vp.and.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = and <16 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x i16> @llvm.vp.and.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = and <2 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t10 = call <4 x i16> @llvm.vp.and.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t11 = and <4 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t12 = call <8 x i16> @llvm.vp.and.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t13 = and <8 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t14 = call <16 x i16> @llvm.vp.and.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t15 = and <16 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t16 = call <2 x i32> @llvm.vp.and.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = and <2 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t19 = and <4 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t21 = and <8 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = call <16 x i32> @llvm.vp.and.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t23 = and <16 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t24 = call <2 x i64> @llvm.vp.and.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t25 = and <2 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = call <4 x i64> @llvm.vp.and.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t27 = and <4 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = call <8 x i64> @llvm.vp.and.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t29 = and <8 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = call <16 x i64> @llvm.vp.and.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t31 = and <16 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t32 = call <vscale x 2 x i8> @llvm.vp.and.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t33 = and <vscale x 2 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t34 = call <vscale x 4 x i8> @llvm.vp.and.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t35 = and <vscale x 4 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t36 = call <vscale x 8 x i8> @llvm.vp.and.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t37 = and <vscale x 8 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t38 = call <vscale x 16 x i8> @llvm.vp.and.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t39 = and <vscale x 16 x i8> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t40 = call <vscale x 2 x i16> @llvm.vp.and.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t41 = and <vscale x 2 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t42 = call <vscale x 4 x i16> @llvm.vp.and.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t43 = and <vscale x 4 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t44 = call <vscale x 8 x i16> @llvm.vp.and.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t45 = and <vscale x 8 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t46 = call <vscale x 16 x i16> @llvm.vp.and.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t47 = and <vscale x 16 x i16> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t48 = call <vscale x 2 x i32> @llvm.vp.and.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t49 = and <vscale x 2 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t50 = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t51 = and <vscale x 4 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t52 = call <vscale x 8 x i32> @llvm.vp.and.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t53 = and <vscale x 8 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t54 = call <vscale x 16 x i32> @llvm.vp.and.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t55 = and <vscale x 16 x i32> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t56 = call <vscale x 2 x i64> @llvm.vp.and.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t57 = and <vscale x 2 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t58 = call <vscale x 4 x i64> @llvm.vp.and.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t59 = and <vscale x 4 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t60 = call <vscale x 8 x i64> @llvm.vp.and.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t61 = and <vscale x 8 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t62 = call <vscale x 16 x i64> @llvm.vp.and.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t63 = and <vscale x 16 x i64> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %t0 = call <2 x i8> @llvm.vp.and.v2i8(<2 x i8> undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+  %t1 = and <2 x i8> undef, undef
+  %t2 = call <4 x i8> @llvm.vp.and.v4i8(<4 x i8> undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+  %t3 = and <4 x i8> undef, undef
+  %t4 = call <8 x i8> @llvm.vp.and.v8i8(<8 x i8> undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+  %t5 = and <8 x i8> undef, undef
+  %t6 = call <16 x i8> @llvm.vp.and.v16i8(<16 x i8> undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+  %t7 = and <16 x i8> undef, undef
+  %t8 = call <2 x i16> @llvm.vp.and.v2i16(<2 x i16> undef, <2 x i16> undef, <2 x i1> undef, i32 undef)
+  %t9 = and <2 x i16> undef, undef
+  %t10 = call <4 x i16> @llvm.vp.and.v4i16(<4 x i16> undef, <4 x i16> undef, <4 x i1> undef, i32 undef)
+  %t11 = and <4 x i16> undef, undef
+  %t12 = call <8 x i16> @llvm.vp.and.v8i16(<8 x i16> undef, <8 x i16> undef, <8 x i1> undef, i32 undef)
+  %t13 = and <8 x i16> undef, undef
+  %t14 = call <16 x i16> @llvm.vp.and.v16i16(<16 x i16> undef, <16 x i16> undef, <16 x i1> undef, i32 undef)
+  %t15 = and <16 x i16> undef, undef
+  %t16 = call <2 x i32> @llvm.vp.and.v2i32(<2 x i32> undef, <2 x i32> undef, <2 x i1> undef, i32 undef)
+  %t17 = and <2 x i32> undef, undef
+  %t18 = call <4 x i32> @llvm.vp.and.v4i32(<4 x i32> undef, <4 x i32> undef, <4 x i1> undef, i32 undef)
+  %t19 = and <4 x i32> undef, undef
+  %t20 = call <8 x i32> @llvm.vp.and.v8i32(<8 x i32> undef, <8 x i32> undef, <8 x i1> undef, i32 undef)
+  %t21 = and <8 x i32> undef, undef
+  %t22 = call <16 x i32> @llvm.vp.and.v16i32(<16 x i32> undef, <16 x i32> undef, <16 x i1> undef, i32 undef)
+  %t23 = and <16 x i32> undef, undef
+  %t24 = call <2 x i64> @llvm.vp.and.v2i64(<2 x i64> undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+  %t25 = and <2 x i64> undef, undef
+  %t26 = call <4 x i64> @llvm.vp.and.v4i64(<4 x i64> undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+  %t27 = and <4 x i64> undef, undef
+  %t28 = call <8 x i64> @llvm.vp.and.v8i64(<8 x i64> undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+  %t29 = and <8 x i64> undef, undef %t30 = call <16 x i64> @llvm.vp.and.v16i64(<16 x i64> undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+  %t31 = and <16 x i64> undef, undef
+  %t32 = call <vscale x 2 x i8> @llvm.vp.and.nxv2i8(<vscale x 2 x i8> undef, <vscale x 2 x i8> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t33 = and <vscale x 2 x i8> undef, undef
+  %t34 = call <vscale x 4 x i8> @llvm.vp.and.nxv4i8(<vscale x 4 x i8> undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t35 = and <vscale x 4 x i8> undef, undef
+  %t36 = call <vscale x 8 x i8> @llvm.vp.and.nxv8i8(<vscale x 8 x i8> undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t37 = and <vscale x 8 x i8> undef, undef
+  %t38 = call <vscale x 16 x i8> @llvm.vp.and.nxv16i8(<vscale x 16 x i8> undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t39 = and <vscale x 16 x i8> undef, undef
+  %t40 = call <vscale x 2 x i16> @llvm.vp.and.nxv2i16(<vscale x 2 x i16> undef, <vscale x 2 x i16> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t41 = and <vscale x 2 x i16> undef, undef
+  %t42 = call <vscale x 4 x i16> @llvm.vp.and.nxv4i16(<vscale x 4 x i16> undef, <vscale x 4 x i16> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t43 = and <vscale x 4 x i16> undef, undef
+  %t44 = call <vscale x 8 x i16> @llvm.vp.and.nxv8i16(<vscale x 8 x i16> undef, <vscale x 8 x i16> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t45 = and <vscale x 8 x i16> undef, undef
+  %t46 = call <vscale x 16 x i16> @llvm.vp.and.nxv16i16(<vscale x 16 x i16> undef, <vscale x 16 x i16> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t47 = and <vscale x 16 x i16> undef, undef
+  %t48 = call <vscale x 2 x i32> @llvm.vp.and.nxv2i32(<vscale x 2 x i32> undef, <vscale x 2 x i32> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t49 = and <vscale x 2 x i32> undef, undef
+  %t50 = call <vscale x 4 x i32> @llvm.vp.and.nxv4i32(<vscale x 4 x i32> undef, <vscale x 4 x i32> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t51 = and <vscale x 4 x i32> undef, undef
+  %t52 = call <vscale x 8 x i32> @llvm.vp.and.nxv8i32(<vscale x 8 x i32> undef, <vscale x 8 x i32> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t53 = and <vscale x 8 x i32> undef, undef
+  %t54 = call <vscale x 16 x i32> @llvm.vp.and.nxv16i32(<vscale x 16 x i32> undef, <vscale x 16 x i32> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t55 = and <vscale x 16 x i32> undef, undef
+  %t56 = call <vscale x 2 x i64> @llvm.vp.and.nxv2i64(<vscale x 2 x i64> undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t57 = and <vscale x 2 x i64> undef, undef
+  %t58 = call <vscale x 4 x i64> @llvm.vp.and.nxv4i64(<vscale x 4 x i64> undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t59 = and <vscale x 4 x i64> undef, undef
+  %t60 = call <vscale x 8 x i64> @llvm.vp.and.nxv8i64(<vscale x 8 x i64> undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t61 = and <vscale x 8 x i64> undef, undef
+  %t62 = call <vscale x 16 x i64> @llvm.vp.and.nxv16i64(<vscale x 16 x i64> undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t63 = and <vscale x 16 x i64> undef, undef
   ret void
 }
 
@@ -312,6 +744,41 @@ define void @abs() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'abs'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %1 = call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 false, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %2 = call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %3 = call <4 x i8> @llvm.vp.abs.v4i8(<4 x i8> undef, i1 false, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %4 = call <4 x i8> @llvm.abs.v4i8(<4 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %5 = call <8 x i8> @llvm.vp.abs.v8i8(<8 x i8> undef, i1 false, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %6 = call <8 x i8> @llvm.abs.v8i8(<8 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 141 for instruction: %7 = call <16 x i8> @llvm.vp.abs.v16i8(<16 x i8> undef, i1 false, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %8 = call <16 x i8> @llvm.abs.v16i8(<16 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 15 for instruction: %9 = call <2 x i64> @llvm.vp.abs.v2i64(<2 x i64> undef, i1 false, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %10 = call <2 x i64> @llvm.abs.v2i64(<2 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 33 for instruction: %11 = call <4 x i64> @llvm.vp.abs.v4i64(<4 x i64> undef, i1 false, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %12 = call <4 x i64> @llvm.abs.v4i64(<4 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 69 for instruction: %13 = call <8 x i64> @llvm.vp.abs.v8i64(<8 x i64> undef, i1 false, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %14 = call <8 x i64> @llvm.abs.v8i64(<8 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 141 for instruction: %15 = call <16 x i64> @llvm.vp.abs.v16i64(<16 x i64> undef, i1 false, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %16 = call <16 x i64> @llvm.abs.v16i64(<16 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %17 = call <vscale x 2 x i8> @llvm.vp.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %18 = call <vscale x 2 x i8> @llvm.abs.nxv2i8(<vscale x 2 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %19 = call <vscale x 4 x i8> @llvm.vp.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %20 = call <vscale x 4 x i8> @llvm.abs.nxv4i8(<vscale x 4 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %21 = call <vscale x 8 x i8> @llvm.vp.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %22 = call <vscale x 8 x i8> @llvm.abs.nxv8i8(<vscale x 8 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %23 = call <vscale x 16 x i8> @llvm.vp.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %24 = call <vscale x 16 x i8> @llvm.abs.nxv16i8(<vscale x 16 x i8> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %25 = call <vscale x 2 x i64> @llvm.vp.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %26 = call <vscale x 2 x i64> @llvm.abs.nxv2i64(<vscale x 2 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %27 = call <vscale x 4 x i64> @llvm.vp.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %28 = call <vscale x 4 x i64> @llvm.abs.nxv4i64(<vscale x 4 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %29 = call <vscale x 8 x i64> @llvm.vp.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %30 = call <vscale x 8 x i64> @llvm.abs.nxv8i64(<vscale x 8 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %31 = call <vscale x 16 x i64> @llvm.vp.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %32 = call <vscale x 16 x i64> @llvm.abs.nxv16i64(<vscale x 16 x i64> undef, i1 false)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call <2 x i8> @llvm.vp.abs.v2i8(<2 x i8> undef, i1 0, <2 x i1> undef, i32 undef)
   call <2 x i8> @llvm.abs.v2i8(<2 x i8> undef, i1 0)
@@ -383,6 +850,41 @@ define void @load() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.load.nxv16i64.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = load <vscale x 16 x i64>, ptr undef, align 128
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'load'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %t0 = call <2 x i8> @llvm.vp.load.v2i8.p0(ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = load <2 x i8>, ptr undef, align 2
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %t2 = call <4 x i8> @llvm.vp.load.v4i8.p0(ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = load <4 x i8>, ptr undef, align 4
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %t4 = call <8 x i8> @llvm.vp.load.v8i8.p0(ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t5 = load <8 x i8>, ptr undef, align 8
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %t6 = call <16 x i8> @llvm.vp.load.v16i8.p0(ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t7 = load <16 x i8>, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %t8 = call <2 x i64> @llvm.vp.load.v2i64.p0(ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = load <2 x i64>, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %t10 = call <4 x i64> @llvm.vp.load.v4i64.p0(ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t12 = load <4 x i64>, ptr undef, align 32
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %t13 = call <8 x i64> @llvm.vp.load.v8i64.p0(ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t14 = load <8 x i64>, ptr undef, align 64
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %t15 = call <16 x i64> @llvm.vp.load.v16i64.p0(ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t16 = load <16 x i64>, ptr undef, align 128
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t17 = call <vscale x 2 x i8> @llvm.vp.load.nxv2i8.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = load <vscale x 2 x i8>, ptr undef, align 2
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t19 = call <vscale x 4 x i8> @llvm.vp.load.nxv4i8.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t20 = load <vscale x 4 x i8>, ptr undef, align 4
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t21 = call <vscale x 8 x i8> @llvm.vp.load.nxv8i8.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t22 = load <vscale x 8 x i8>, ptr undef, align 8
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t23 = call <vscale x 16 x i8> @llvm.vp.load.nxv16i8.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t24 = load <vscale x 16 x i8>, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t25 = call <vscale x 2 x i64> @llvm.vp.load.nxv2i64.p0(ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = load <vscale x 2 x i64>, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t27 = call <vscale x 4 x i64> @llvm.vp.load.nxv4i64.p0(ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = load <vscale x 4 x i64>, ptr undef, align 32
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t29 = call <vscale x 8 x i64> @llvm.vp.load.nxv8i64.p0(ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = load <vscale x 8 x i64>, ptr undef, align 64
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.vp.load.nxv16i64.p0(ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = load <vscale x 16 x i64>, ptr undef, align 128
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.vp.load.v2i8(ptr undef, <2 x i1> undef, i32 undef)
   %t1 = load <2 x i8>, ptr undef
@@ -454,6 +956,41 @@ define void @store() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: call void @llvm.vp.store.nxv16i64.p0(<vscale x 16 x i64> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 16 x i64> undef, ptr undef, align 128
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'store'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i8.p0(<2 x i8> undef, ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i8> undef, ptr undef, align 2
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.vp.store.v4i8.p0(<4 x i8> undef, ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <4 x i8> undef, ptr undef, align 4
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.vp.store.v8i8.p0(<8 x i8> undef, ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <8 x i8> undef, ptr undef, align 8
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.vp.store.v16i8.p0(<16 x i8> undef, ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <16 x i8> undef, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.vp.store.v2i64.p0(<2 x i64> undef, ptr undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <2 x i64> undef, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.vp.store.v4i64.p0(<4 x i64> undef, ptr undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <4 x i64> undef, ptr undef, align 32
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.vp.store.v8i64.p0(<8 x i64> undef, ptr undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <8 x i64> undef, ptr undef, align 64
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.vp.store.v16i64.p0(<16 x i64> undef, ptr undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <16 x i64> undef, ptr undef, align 128
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv2i8.p0(<vscale x 2 x i8> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 2 x i8> undef, ptr undef, align 2
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv4i8.p0(<vscale x 4 x i8> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 4 x i8> undef, ptr undef, align 4
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv8i8.p0(<vscale x 8 x i8> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: store <vscale x 8 x i8> undef, ptr undef, align 8
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv16i8.p0(<vscale x 16 x i8> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 16 x i8> undef, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv2i64.p0(<vscale x 2 x i64> undef, ptr undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: store <vscale x 2 x i64> undef, ptr undef, align 16
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv4i64.p0(<vscale x 4 x i64> undef, ptr undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: store <vscale x 4 x i64> undef, ptr undef, align 32
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv8i64.p0(<vscale x 8 x i64> undef, ptr undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: store <vscale x 8 x i64> undef, ptr undef, align 64
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.vp.store.nxv16i64.p0(<vscale x 16 x i64> undef, ptr undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: store <vscale x 16 x i64> undef, ptr undef, align 128
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.vp.store.v2i8(<2 x i8> undef, ptr undef, <2 x i1> undef, i32 undef)
   store <2 x i8> undef, ptr undef
@@ -513,6 +1050,29 @@ define void @strided_load() {
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t29 = call <vscale x 8 x i64> @llvm.experimental.vp.strided.load.nxv8i64.p0.i64(ptr undef, i64 undef, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.experimental.vp.strided.load.nxv16i64.p0.i64(ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'strided_load'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %t0 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.p0.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %t2 = call <4 x i8> @llvm.experimental.vp.strided.load.v4i8.p0.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %t4 = call <8 x i8> @llvm.experimental.vp.strided.load.v8i8.p0.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %t6 = call <16 x i8> @llvm.experimental.vp.strided.load.v16i8.p0.i64(ptr undef, i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %t8.a = call <2 x i64> @llvm.experimental.vp.strided.load.v2i64.p0.i64(ptr align 8 undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %t10.a = call <4 x i64> @llvm.experimental.vp.strided.load.v4i64.p0.i64(ptr align 8 undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %t13.a = call <8 x i64> @llvm.experimental.vp.strided.load.v8i64.p0.i64(ptr align 8 undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %t15.a = call <16 x i64> @llvm.experimental.vp.strided.load.v16i64.p0.i64(ptr align 8 undef, i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %t8 = call <2 x i64> @llvm.experimental.vp.strided.load.v2i64.p0.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %t10 = call <4 x i64> @llvm.experimental.vp.strided.load.v4i64.p0.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %t13 = call <8 x i64> @llvm.experimental.vp.strided.load.v8i64.p0.i64(ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %t15 = call <16 x i64> @llvm.experimental.vp.strided.load.v16i64.p0.i64(ptr undef, i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t17 = call <vscale x 2 x i8> @llvm.experimental.vp.strided.load.nxv2i8.p0.i64(ptr undef, i64 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t19 = call <vscale x 4 x i8> @llvm.experimental.vp.strided.load.nxv4i8.p0.i64(ptr undef, i64 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t21 = call <vscale x 8 x i8> @llvm.experimental.vp.strided.load.nxv8i8.p0.i64(ptr undef, i64 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t23 = call <vscale x 16 x i8> @llvm.experimental.vp.strided.load.nxv16i8.p0.i64(ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t25 = call <vscale x 2 x i64> @llvm.experimental.vp.strided.load.nxv2i64.p0.i64(ptr undef, i64 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t27 = call <vscale x 4 x i64> @llvm.experimental.vp.strided.load.nxv4i64.p0.i64(ptr undef, i64 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t29 = call <vscale x 8 x i64> @llvm.experimental.vp.strided.load.nxv8i64.p0.i64(ptr undef, i64 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %t31 = call <vscale x 16 x i64> @llvm.experimental.vp.strided.load.nxv16i64.p0.i64(ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   %t0 = call <2 x i8> @llvm.experimental.vp.strided.load.v2i8.i64(ptr undef, i64 undef, <2 x i1> undef, i32 undef)
   %t2 = call <4 x i8> @llvm.experimental.vp.strided.load.v4i8.i64(ptr undef, i64 undef, <4 x i1> undef, i32 undef)
@@ -560,6 +1120,29 @@ define void @strided_store() {
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv8i64.p0.i64(<vscale x 8 x i64> undef, ptr undef, i64 undef, <vscale x 8 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv16i64.p0.i64(<vscale x 16 x i64> undef, ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'strided_store'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i8.p0.i64(<2 x i8> undef, ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.experimental.vp.strided.store.v4i8.p0.i64(<4 x i8> undef, ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.experimental.vp.strided.store.v8i8.p0.i64(<8 x i8> undef, ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.experimental.vp.strided.store.v16i8.p0.i64(<16 x i8> undef, ptr undef, i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i64.p0.i64(<2 x i64> undef, ptr undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.experimental.vp.strided.store.v4i64.p0.i64(<4 x i64> undef, ptr undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.experimental.vp.strided.store.v8i64.p0.i64(<8 x i64> undef, ptr undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.experimental.vp.strided.store.v16i64.p0.i64(<16 x i64> undef, ptr undef, i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: call void @llvm.experimental.vp.strided.store.v2i64.p0.i64(<2 x i64> undef, ptr align 8 undef, i64 undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: call void @llvm.experimental.vp.strided.store.v4i64.p0.i64(<4 x i64> undef, ptr align 8 undef, i64 undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: call void @llvm.experimental.vp.strided.store.v8i64.p0.i64(<8 x i64> undef, ptr align 8 undef, i64 undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: call void @llvm.experimental.vp.strided.store.v16i64.p0.i64(<16 x i64> undef, ptr align 8 undef, i64 undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv2i8.p0.i64(<vscale x 2 x i8> undef, ptr undef, i64 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv4i8.p0.i64(<vscale x 4 x i8> undef, ptr undef, i64 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv8i8.p0.i64(<vscale x 8 x i8> undef, ptr undef, i64 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv16i8.p0.i64(<vscale x 16 x i8> undef, ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv2i64.p0.i64(<vscale x 2 x i64> undef, ptr undef, i64 undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv4i64.p0.i64(<vscale x 4 x i64> undef, ptr undef, i64 undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv8i64.p0.i64(<vscale x 8 x i64> undef, ptr undef, i64 undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: call void @llvm.experimental.vp.strided.store.nxv16i64.p0.i64(<vscale x 16 x i64> undef, ptr undef, i64 undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call void @llvm.experimental.vp.strided.store.v2i8.i64(<2 x i8> undef, ptr undef, i64 undef, <2 x i1> undef, i32 undef)
   call void @llvm.experimental.vp.strided.store.v4i8.i64(<4 x i8> undef, ptr undef, i64 undef, <4 x i1> undef, i32 undef)
@@ -621,6 +1204,41 @@ define void @reduce_add() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %31 = call i64 @llvm.vp.reduce.add.nxv16i64(i64 undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %32 = call i64 @llvm.vector.reduce.add.nxv16i64(<vscale x 16 x i64> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'reduce_add'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %1 = call i8 @llvm.vp.reduce.add.v2i8(i8 undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %2 = call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %3 = call i8 @llvm.vp.reduce.add.v4i8(i8 undef, <4 x i8> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %4 = call i8 @llvm.vector.reduce.add.v4i8(<4 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %5 = call i8 @llvm.vp.reduce.add.v8i8(i8 undef, <8 x i8> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %6 = call i8 @llvm.vector.reduce.add.v8i8(<8 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %7 = call i8 @llvm.vp.reduce.add.v16i8(i8 undef, <16 x i8> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %8 = call i8 @llvm.vector.reduce.add.v16i8(<16 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %9 = call i64 @llvm.vp.reduce.add.v2i64(i64 undef, <2 x i64> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 3 for instruction: %10 = call i64 @llvm.vector.reduce.add.v2i64(<2 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %11 = call i64 @llvm.vp.reduce.add.v4i64(i64 undef, <4 x i64> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %12 = call i64 @llvm.vector.reduce.add.v4i64(<4 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %13 = call i64 @llvm.vp.reduce.add.v8i64(i64 undef, <8 x i64> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %14 = call i64 @llvm.vector.reduce.add.v8i64(<8 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %15 = call i64 @llvm.vp.reduce.add.v16i64(i64 undef, <16 x i64> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %16 = call i64 @llvm.vector.reduce.add.v16i64(<16 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %17 = call i8 @llvm.vp.reduce.add.nxv8i8(i8 undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %18 = call i8 @llvm.vector.reduce.add.nxv2i8(<vscale x 2 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %19 = call i8 @llvm.vp.reduce.add.nxv4i8(i8 undef, <vscale x 4 x i8> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %20 = call i8 @llvm.vector.reduce.add.nxv4i8(<vscale x 4 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %21 = call i8 @llvm.vp.reduce.add.nxv8i8(i8 undef, <vscale x 8 x i8> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %22 = call i8 @llvm.vector.reduce.add.nxv8i8(<vscale x 8 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %23 = call i8 @llvm.vp.reduce.add.nxv16i8(i8 undef, <vscale x 16 x i8> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 7 for instruction: %24 = call i8 @llvm.vector.reduce.add.nxv16i8(<vscale x 16 x i8> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %25 = call i64 @llvm.vp.reduce.add.nxv2i64(i64 undef, <vscale x 2 x i64> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %26 = call i64 @llvm.vector.reduce.add.nxv2i64(<vscale x 2 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %27 = call i64 @llvm.vp.reduce.add.nxv4i64(i64 undef, <vscale x 4 x i64> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 5 for instruction: %28 = call i64 @llvm.vector.reduce.add.nxv4i64(<vscale x 4 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %29 = call i64 @llvm.vp.reduce.add.nxv8i64(i64 undef, <vscale x 8 x i64> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %30 = call i64 @llvm.vector.reduce.add.nxv8i64(<vscale x 8 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %31 = call i64 @llvm.vp.reduce.add.nxv16i64(i64 undef, <vscale x 16 x i64> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 14 for instruction: %32 = call i64 @llvm.vector.reduce.add.nxv16i64(<vscale x 16 x i64> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call i8 @llvm.vp.reduce.add.v2i8(i8 undef, <2 x i8> undef, <2 x i1> undef, i32 undef)
   call i8 @llvm.vector.reduce.add.v2i8(<2 x i8> undef)
@@ -692,6 +1310,41 @@ define void @reduce_fadd() {
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %31 = call double @llvm.vp.reduce.fadd.nxv16f64(double undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %32 = call double @llvm.vector.reduce.fadd.nxv16f64(double undef, <vscale x 16 x double> undef)
 ; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'reduce_fadd'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %1 = call float @llvm.vp.reduce.fadd.v2f32(float undef, <2 x float> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %2 = call float @llvm.vector.reduce.fadd.v2f32(float undef, <2 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %3 = call float @llvm.vp.reduce.fadd.v4f32(float undef, <4 x float> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %4 = call float @llvm.vector.reduce.fadd.v4f32(float undef, <4 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %5 = call float @llvm.vp.reduce.fadd.v8f32(float undef, <8 x float> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %6 = call float @llvm.vector.reduce.fadd.v8f32(float undef, <8 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %7 = call float @llvm.vp.reduce.fadd.v16f32(float undef, <16 x float> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %8 = call float @llvm.vector.reduce.fadd.v16f32(float undef, <16 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 12 for instruction: %9 = call double @llvm.vp.reduce.fadd.v2f64(double undef, <2 x double> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %10 = call double @llvm.vector.reduce.fadd.v2f64(double undef, <2 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 26 for instruction: %11 = call double @llvm.vp.reduce.fadd.v4f64(double undef, <4 x double> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %12 = call double @llvm.vector.reduce.fadd.v4f64(double undef, <4 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 54 for instruction: %13 = call double @llvm.vp.reduce.fadd.v8f64(double undef, <8 x double> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %14 = call double @llvm.vector.reduce.fadd.v8f64(double undef, <8 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 110 for instruction: %15 = call double @llvm.vp.reduce.fadd.v16f64(double undef, <16 x double> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %16 = call double @llvm.vector.reduce.fadd.v16f64(double undef, <16 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %17 = call float @llvm.vp.reduce.fadd.nxv2f32(float undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %18 = call float @llvm.vector.reduce.fadd.nxv2f32(float undef, <vscale x 2 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %19 = call float @llvm.vp.reduce.fadd.nxv4f32(float undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %20 = call float @llvm.vector.reduce.fadd.nxv4f32(float undef, <vscale x 4 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %21 = call float @llvm.vp.reduce.fadd.nxv8f32(float undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %22 = call float @llvm.vector.reduce.fadd.nxv8f32(float undef, <vscale x 8 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %23 = call float @llvm.vp.reduce.fadd.nxv16f32(float undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %24 = call float @llvm.vector.reduce.fadd.nxv16f32(float undef, <vscale x 16 x float> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %25 = call double @llvm.vp.reduce.fadd.nxv2f64(double undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 6 for instruction: %26 = call double @llvm.vector.reduce.fadd.nxv2f64(double undef, <vscale x 2 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %27 = call double @llvm.vp.reduce.fadd.nxv4f64(double undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 10 for instruction: %28 = call double @llvm.vector.reduce.fadd.nxv4f64(double undef, <vscale x 4 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %29 = call double @llvm.vp.reduce.fadd.nxv8f64(double undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 18 for instruction: %30 = call double @llvm.vector.reduce.fadd.nxv8f64(double undef, <vscale x 8 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Invalid cost for instruction: %31 = call double @llvm.vp.reduce.fadd.nxv16f64(double undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 34 for instruction: %32 = call double @llvm.vector.reduce.fadd.nxv16f64(double undef, <vscale x 16 x double> undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
 ;
   call float @llvm.vp.reduce.fadd.v2f32(float undef, <2 x float> undef, <2 x i1> undef, i32 undef)
   call float @llvm.vector.reduce.fadd.v2f32(float undef, <2 x float> undef)
@@ -728,6 +1381,114 @@ define void @reduce_fadd() {
   ret void
 }
 
+define void @vp_fadd(){
+; CHECK-LABEL: 'vp_fadd'
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x float> @llvm.vp.fadd.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = fadd <2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = fadd <4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t4 = call <8 x float> @llvm.vp.fadd.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t5 = fadd <8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t6 = call <16 x float> @llvm.vp.fadd.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t7 = fadd <16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x double> @llvm.vp.fadd.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = fadd <2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t10 = call <4 x double> @llvm.vp.fadd.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t11 = fadd <4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t12 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t13 = fadd <8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t14 = call <16 x double> @llvm.vp.fadd.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t15 = fadd <16 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = call <vscale x 2 x float> @llvm.vp.fadd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = fadd <vscale x 2 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t19 = call <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = fadd <vscale x 4 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t21 = call <vscale x 8 x float> @llvm.vp.fadd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = fadd <vscale x 8 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t23 = call <vscale x 16 x float> @llvm.vp.fadd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t24 = fadd <vscale x 16 x float> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t25 = call <vscale x 2 x double> @llvm.vp.fadd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = fadd <vscale x 2 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t27 = call <vscale x 4 x double> @llvm.vp.fadd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = fadd <vscale x 4 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t29 = call <vscale x 8 x double> @llvm.vp.fadd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = fadd <vscale x 8 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x double> @llvm.vp.fadd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = fadd <vscale x 16 x double> undef, undef
+; CHECK-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+; TYPEBASED-LABEL: 'vp_fadd'
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t0 = call <2 x float> @llvm.vp.fadd.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t1 = fadd <2 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t2 = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t3 = fadd <4 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t4 = call <8 x float> @llvm.vp.fadd.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t5 = fadd <8 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t6 = call <16 x float> @llvm.vp.fadd.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t7 = fadd <16 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t8 = call <2 x double> @llvm.vp.fadd.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t9 = fadd <2 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t10 = call <4 x double> @llvm.vp.fadd.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t11 = fadd <4 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t12 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t13 = fadd <8 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t14 = call <16 x double> @llvm.vp.fadd.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t15 = fadd <16 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t17 = call <vscale x 2 x float> @llvm.vp.fadd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 1 for instruction: %t18 = fadd <vscale x 2 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t19 = call <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t20 = fadd <vscale x 4 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t21 = call <vscale x 8 x float> @llvm.vp.fadd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t22 = fadd <vscale x 8 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t23 = call <vscale x 16 x float> @llvm.vp.fadd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t24 = fadd <vscale x 16 x float> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t25 = call <vscale x 2 x double> @llvm.vp.fadd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 2 for instruction: %t26 = fadd <vscale x 2 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t27 = call <vscale x 4 x double> @llvm.vp.fadd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 4 for instruction: %t28 = fadd <vscale x 4 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t29 = call <vscale x 8 x double> @llvm.vp.fadd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 8 for instruction: %t30 = fadd <vscale x 8 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t31 = call <vscale x 16 x double> @llvm.vp.fadd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 16 for instruction: %t32 = fadd <vscale x 16 x double> undef, undef
+; TYPEBASED-NEXT:  Cost Model: Found an estimated cost of 0 for instruction: ret void
+;
+  %t0 = call <2 x float> @llvm.vp.fadd.v2f32(<2 x float> undef, <2 x float> undef, <2 x i1> undef, i32 undef)
+  %t1 = fadd <2 x float> undef, undef
+  %t2 = call <4 x float> @llvm.vp.fadd.v4f32(<4 x float> undef, <4 x float> undef, <4 x i1> undef, i32 undef)
+  %t3 = fadd <4 x float> undef, undef
+  %t4 = call <8 x float> @llvm.vp.fadd.v8f32(<8 x float> undef, <8 x float> undef, <8 x i1> undef, i32 undef)
+  %t5 = fadd <8 x float> undef, undef
+  %t6 = call <16 x float> @llvm.vp.fadd.v16f32(<16 x float> undef, <16 x float> undef, <16 x i1> undef, i32 undef)
+  %t7 = fadd <16 x float> undef, undef
+  %t8 = call <2 x double> @llvm.vp.fadd.v2f64(<2 x double> undef, <2 x double> undef, <2 x i1> undef, i32 undef)
+  %t9 = fadd <2 x double> undef, undef
+  %t10 = call <4 x double> @llvm.vp.fadd.v4f64(<4 x double> undef, <4 x double> undef, <4 x i1> undef, i32 undef)
+  %t11 = fadd <4 x double> undef, undef
+  %t12 = call <8 x double> @llvm.vp.fadd.v8f64(<8 x double> undef, <8 x double> undef, <8 x i1> undef, i32 undef)
+  %t13 = fadd <8 x double> undef, undef
+  %t14 = call <16 x double> @llvm.vp.fadd.v16f64(<16 x double> undef, <16 x double> undef, <16 x i1> undef, i32 undef)
+  %t15 = fadd <16 x double> undef, undef
+  %t17 = call <vscale x 2 x float> @llvm.vp.fadd.nxv2f32(<vscale x 2 x float> undef, <vscale x 2 x float> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t18 = fadd <vscale x 2 x float> undef, undef
+  %t19 = call <vscale x 4 x float> @llvm.vp.fadd.nxv4f32(<vscale x 4 x float> undef, <vscale x 4 x float> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t20 = fadd <vscale x 4 x float> undef, undef
+  %t21 = call <vscale x 8 x float> @llvm.vp.fadd.nxv8f32(<vscale x 8 x float> undef, <vscale x 8 x float> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t22 = fadd <vscale x 8 x float> undef, undef
+  %t23 = call <vscale x 16 x float> @llvm.vp.fadd.nxv16f32(<vscale x 16 x float> undef, <vscale x 16 x float> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t24 = fadd <vscale x 16 x float> undef, undef
+  %t25 = call <vscale x 2 x double> @llvm.vp.fadd.nxv2f64(<vscale x 2 x double> undef, <vscale x 2 x double> undef, <vscale x 2 x i1> undef, i32 undef)
+  %t26 = fadd <vscale x 2 x double> undef, undef
+  %t27 = call <vscale x 4 x double> @llvm.vp.fadd.nxv4f64(<vscale x 4 x double> undef, <vscale x 4 x double> undef, <vscale x 4 x i1> undef, i32 undef)
+  %t28 = fadd <vscale x 4 x double> undef, undef
+  %t29 = call <vscale x 8 x double> @llvm.vp.fadd.nxv8f64(<vscale x 8 x double> undef, <vscale x 8 x double> undef, <vscale x 8 x i1> undef, i32 undef)
+  %t30 = fadd <vscale x 8 x double> undef, undef
+  %t31 = call <vscale x 16 x double> @llvm.vp.fadd.nxv16f64(<vscale x 16 x double> undef, <vscale x 16 x double> undef, <vscale x 16 x i1> undef, i32 undef)
+  %t32 = fadd <vscale x 16 x double> undef, undef
+
+  ret void
+}
+
+
 declare <2 x i8> @llvm.vp.add.v2i8(<2 x i8>, <2 x i8>, <2 x i1>, i32)
 declare <4 x i8> @llvm.vp.add.v4i8(<4 x i8>, <4 x i8>, <4 x i1>, i32)
 declare <8 x i8> @llvm.vp.add.v8i8(<8 x i8>, <8 x i8>, <8 x i1>, i32)

diff  --git a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
index 7dc0ba50c1f8c8..03fbb5e5a4674c 100644
--- a/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
+++ b/llvm/test/Transforms/VectorCombine/RISCV/vpintrin-scalarization.ll
@@ -37,14 +37,14 @@ declare <1 x i64> @llvm.vp.mul.v1i64(<1 x i64>, <1 x i64>, <1 x i1>, i32)
 declare <4 x i64> @llvm.vp.mul.v4i64(<4 x i64>, <4 x i64>, <4 x i1>, i32)
 
 define <vscale x 1 x i64> @add_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @add_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = add i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @add_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = add i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @add_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -54,6 +54,15 @@ define <vscale x 1 x i64> @add_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.add.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @add_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.add.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -80,14 +89,14 @@ define <vscale x 1 x i64> @add_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
 }
 
 define <vscale x 1 x i64> @sub_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @sub_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = sub i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @sub_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = sub i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @sub_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -97,6 +106,15 @@ define <vscale x 1 x i64> @sub_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sub.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @sub_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sub.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -123,14 +141,14 @@ define <vscale x 1 x i64> @sub_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
 }
 
 define <vscale x 1 x i64> @mul_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @mul_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = mul i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @mul_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = mul i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @mul_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -140,6 +158,15 @@ define <vscale x 1 x i64> @mul_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @mul_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -166,14 +193,14 @@ define <vscale x 1 x i64> @mul_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
 }
 
 define <vscale x 1 x i64> @sdiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @sdiv_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = sdiv i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @sdiv_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = sdiv i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @sdiv_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -183,6 +210,15 @@ define <vscale x 1 x i64> @sdiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sdiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @sdiv_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.sdiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -230,14 +266,14 @@ define <vscale x 1 x i64> @sdiv_nxv1i64_unspeculatable(i64 %x, i64 %y, i32 zeroe
 }
 
 define <vscale x 1 x i64> @udiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @udiv_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = udiv i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @udiv_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = udiv i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @udiv_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -247,6 +283,15 @@ define <vscale x 1 x i64> @udiv_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.udiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @udiv_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.udiv.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -294,14 +339,14 @@ define <vscale x 1 x i64> @udiv_nxv1i64_unspeculatable(i64 %x, i64 %y, i32 zeroe
 }
 
 define <vscale x 1 x i64> @srem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @srem_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = srem i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @srem_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = srem i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @srem_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -311,6 +356,15 @@ define <vscale x 1 x i64> @srem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.srem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @srem_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.srem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -358,14 +412,14 @@ define <vscale x 1 x i64> @srem_nxv1i64_unspeculatable(i64 %x, i64 %y, i32 zeroe
 }
 
 define <vscale x 1 x i64> @urem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @urem_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = urem i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @urem_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = urem i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @urem_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -375,6 +429,15 @@ define <vscale x 1 x i64> @urem_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.urem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @urem_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.urem.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -598,14 +661,14 @@ define <vscale x 1 x i64> @urem_nxv1i64_anymask_knownvl(i64 %x, i64 %y, <vscale
 }
 
 define <vscale x 1 x i64> @ashr_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @ashr_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = ashr i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @ashr_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = ashr i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @ashr_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -615,6 +678,15 @@ define <vscale x 1 x i64> @ashr_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.ashr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @ashr_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.ashr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -641,14 +713,14 @@ define <vscale x 1 x i64> @ashr_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
 }
 
 define <vscale x 1 x i64> @lshr_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @lshr_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = lshr i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @lshr_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = lshr i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @lshr_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -658,6 +730,15 @@ define <vscale x 1 x i64> @lshr_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.lshr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @lshr_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.lshr.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -684,14 +765,14 @@ define <vscale x 1 x i64> @lshr_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
 }
 
 define <vscale x 1 x i64> @shl_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @shl_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = shl i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @shl_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = shl i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @shl_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -701,6 +782,15 @@ define <vscale x 1 x i64> @shl_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.shl.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @shl_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.shl.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -727,14 +817,14 @@ define <vscale x 1 x i64> @shl_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
 }
 
 define <vscale x 1 x i64> @or_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @or_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = or i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @or_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = or i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @or_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -744,6 +834,15 @@ define <vscale x 1 x i64> @or_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y,
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.or.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @or_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.or.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -770,14 +869,14 @@ define <vscale x 1 x i64> @or_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <vs
 }
 
 define <vscale x 1 x i64> @and_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @and_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = and i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @and_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = and i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @and_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -787,6 +886,15 @@ define <vscale x 1 x i64> @and_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.and.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @and_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.and.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -813,14 +921,14 @@ define <vscale x 1 x i64> @and_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <v
 }
 
 define <vscale x 1 x i64> @xor_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @xor_nxv1i64_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = xor i64 [[Y:%.*]], 42
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
+; VEC-COMBINE-64-LABEL: @xor_nxv1i64_allonesmask(
+; VEC-COMBINE-64-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-64-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP1:%.*]] = xor i64 [[Y:%.*]], 42
+; VEC-COMBINE-64-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[TMP1]], i64 0
+; VEC-COMBINE-64-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[DOTSPLATINSERT]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-64-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-64-NEXT:    ret <vscale x 1 x i64> [[TMP3]]
 ;
 ; NO-VEC-COMBINE-LABEL: @xor_nxv1i64_allonesmask(
 ; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
@@ -830,6 +938,15 @@ define <vscale x 1 x i64> @xor_nxv1i64_allonesmask(<vscale x 1 x i64> %x, i64 %y
 ; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.xor.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
 ; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
 ; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
+;
+; VEC-COMBINE-32-LABEL: @xor_nxv1i64_allonesmask(
+; VEC-COMBINE-32-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; VEC-COMBINE-32-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x i64> poison, i64 [[Y:%.*]], i64 0
+; VEC-COMBINE-32-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x i64> [[TMP1]], <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer
+; VEC-COMBINE-32-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x i64> @llvm.vp.xor.nxv1i64(<vscale x 1 x i64> [[TMP2]], <vscale x 1 x i64> shufflevector (<vscale x 1 x i64> insertelement (<vscale x 1 x i64> poison, i64 42, i64 0), <vscale x 1 x i64> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; VEC-COMBINE-32-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x i64> @llvm.vp.mul.nxv1i64(<vscale x 1 x i64> [[X:%.*]], <vscale x 1 x i64> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; VEC-COMBINE-32-NEXT:    ret <vscale x 1 x i64> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1013,23 +1130,14 @@ define <vscale x 1 x i64> @umax_nxv1i64_anymask(<vscale x 1 x i64> %x, i64 %y, <
 }
 
 define <vscale x 1 x float> @fadd_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fadd_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = fadd float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fadd_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fadd_nxv1f32_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x float> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1056,23 +1164,14 @@ define <vscale x 1 x float> @fadd_nxv1f32_anymask(<vscale x 1 x float> %x, float
 }
 
 define <vscale x 1 x float> @fsub_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fsub_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = fsub float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fsub_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fsub.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fsub_nxv1f32_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fsub.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x float> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1099,23 +1198,14 @@ define <vscale x 1 x float> @fsub_nxv1f32_anymask(<vscale x 1 x float> %x, float
 }
 
 define <vscale x 1 x float> @fdiv_nxv1f32_allonesmask(<vscale x 1 x float> %x, float %y, i32 zeroext %evl) {
-; VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = fdiv float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fdiv_nxv1f32_allonesmask(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 [[EVL:%.*]])
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 [[EVL]])
+; ALL-NEXT:    ret <vscale x 1 x float> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
@@ -1185,23 +1275,14 @@ define <vscale x 1 x float> @frem_nxv1f32_allonesmask(<vscale x 1 x float> %x, f
 }
 
 define <vscale x 1 x float> @fdiv_nxv1f32_allonesmask_knownvl(<vscale x 1 x float> %x, float %y) {
-; VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask_knownvl(
-; VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP1:%.*]] = fdiv float [[Y:%.*]], 4.200000e+01
-; VEC-COMBINE-NEXT:    [[DOTSPLATINSERT:%.*]] = insertelement <vscale x 1 x float> poison, float [[TMP1]], i64 0
-; VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[DOTSPLATINSERT]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP2]], <vscale x 1 x i1> [[MASK]], i32 4)
-; VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP3]]
-;
-; NO-VEC-COMBINE-LABEL: @fdiv_nxv1f32_allonesmask_knownvl(
-; NO-VEC-COMBINE-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
-; NO-VEC-COMBINE-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
-; NO-VEC-COMBINE-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
-; NO-VEC-COMBINE-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 4)
-; NO-VEC-COMBINE-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 4)
-; NO-VEC-COMBINE-NEXT:    ret <vscale x 1 x float> [[TMP4]]
+; ALL-LABEL: @fdiv_nxv1f32_allonesmask_knownvl(
+; ALL-NEXT:    [[SPLAT:%.*]] = insertelement <vscale x 1 x i1> poison, i1 true, i32 0
+; ALL-NEXT:    [[MASK:%.*]] = shufflevector <vscale x 1 x i1> [[SPLAT]], <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP1:%.*]] = insertelement <vscale x 1 x float> poison, float [[Y:%.*]], i64 0
+; ALL-NEXT:    [[TMP2:%.*]] = shufflevector <vscale x 1 x float> [[TMP1]], <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer
+; ALL-NEXT:    [[TMP3:%.*]] = call <vscale x 1 x float> @llvm.vp.fdiv.nxv1f32(<vscale x 1 x float> [[TMP2]], <vscale x 1 x float> shufflevector (<vscale x 1 x float> insertelement (<vscale x 1 x float> poison, float 4.200000e+01, i64 0), <vscale x 1 x float> poison, <vscale x 1 x i32> zeroinitializer), <vscale x 1 x i1> [[MASK]], i32 4)
+; ALL-NEXT:    [[TMP4:%.*]] = call <vscale x 1 x float> @llvm.vp.fadd.nxv1f32(<vscale x 1 x float> [[X:%.*]], <vscale x 1 x float> [[TMP3]], <vscale x 1 x i1> [[MASK]], i32 4)
+; ALL-NEXT:    ret <vscale x 1 x float> [[TMP4]]
 ;
   %splat = insertelement <vscale x 1 x i1> poison, i1 -1, i32 0
   %mask = shufflevector <vscale x 1 x i1> %splat, <vscale x 1 x i1> poison, <vscale x 1 x i32> zeroinitializer


        


More information about the llvm-commits mailing list